Introduction:

Prostate cancer (PCa) remains a leading cause of cancer-related mortality among men. The integration of multiparametric MRI (mpMRI) in diagnosing clinically significant prostate cancer (csPCa) has revolutionized management, enabling more precise lesion identification and reduction in unnecessary biopsies. The Prostate Imaging-Reporting and Data System (PI-RADS) is a validated mpMRI scoring system that helps to inform probability of discovering csPCa on targeted prostate biopsy. Our study aims to develop and validate an updated PI-RADS v2.1-based predictive model for csPCa diagnosis and compare its performance with existing models.

Methods:

We retrospectively analyzed data from patients who underwent mpMRI assessment using the PI-RADS v2.1 scoring system and biopsy between April 2019 and December 2023. Two models were developed: a ‘Clinical Baseline’ model using patient demographics and laboratory results, and an ‘MRI Added’ model incorporating PI-RADS v2.1 scores and prostate volumes. These models were validated on internal and external cohorts and compared against two previously published MRI-based algorithms by Mehralivand et al. and van Leeuwen et al. for predicting csPCa using AUC and decision curve analysis.

Results:

A total of 1319 patients were included across our internal and external cohorts. The ‘MRI Added’ model showed significantly improved discriminative ability (AUC_internal 0.88, AUC_external 0.79) compared to the ‘Clinical Baseline’ model (AUC_internal 0.75, AUC_external 0.68) (p < .001) (Fig. 1). It demonstrated higher net benefits across various clinical thresholds, reducing unnecessary biopsies by 27% in internal and 10% in external cohorts at a 25% risk threshold. However, there was no significant difference in AUC between our model and the compared models from Mehralivand et al. and van Leeuwen et al. developed for PI-RADS v2 and v1, respectively.

Conclusion:

Our PI-RADS v2.1-based mpMRI model significantly enhances csPCa prediction, outperforming the traditional clinical model in accuracy and reduction of unnecessary biopsies. It shows promise across diverse patient populations, establishing an updated integrated approach for prostate cancer detection and management.

Funding: Intramural Research Program of the NCI, NIH